README.md

metadata

language_details: quy_Latn, spa_Latn
pipeline_tag: translation
tags:
  - nllb
license: cc-by-nc-4.0
inference: false

Description

Finetuned facebook/nllb-200-3.3B model to translate between Spanish ("spa_Latn") and Mapuzungun ("quy_Latn").

Example

from transformers import NllbTokenizer, AutoModelForSeq2SeqLM

tokenizer = NllbTokenizer.from_pretrained("CenIA/nllb-200-3.3B-spa-arn", use_auth_token="HF_TOKEN")
model = AutoModelForSeq2SeqLM.from_pretrained("CenIA/nllb-200-3.3B-spa-arn", use_auth_token="HF_TOKEN")

def translate(sentence: str, translate_from="spa_Latn", translate_to="quy_Latn") -> str:
    tokenizer.src_lang = translate_from
    tokenizer.tgt_lang = translate_to

    inputs = tokenizer(sentence, return_tensors="pt")
    result = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id[translate_to])
    decoded = tokenizer.batch_decode(result, skip_special_tokens=True)[0]

    return decoded

traduction = translate("Hola, ¿cómo estás?")

print(traduction)